Raehoshi Illust XL

an enhanced iteration built upon the Illustrious XL v01 model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made, and further refinements will continue. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.

Enjoying my work? Consider supporting the development of my models by buying me a coffee on Ko-fi

Recommended setting

Positive prompt :

masterpiece, best quality, good quality,

Negative prompt :

(bad quality, worst quality:1.2), lowres, bad anatomy, sketch, jpeg artifacts, ugly, poorly drawn, signature, watermark,

*Optional: If you notice excessive noise or artifacts in the background, try adding "film grain" to the negative prompt to reduce it.

Steps : 28

CFG : 5-7

Sampler : euler_a

Supported resolution :

1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536

Training Details

The model was developed using a two-stage fine-tuning process. In Stage 1, new series and characters were introduced into the model. Stage 2 focused on fixing issues and enhancing the overall style for improved output.

Stage 1

• Dataset : 31k

• Hardware : 2x A100 80gb

• Batch size : 32

• Gradient accumulation steps : 2

• Learning rate : 6e-6

• Text encoder : 3e-6

• Epoch : 15

Stage 2

• Dataset : 2.5k

• Hardware : 1x A100 80gb

• Batch size : 48

• Gradient accumulation steps : 1

• Learning rate : 3e-6

• Text encoder : disable

• Epoch : 15

List of New Series/Characters Trained:

• zenless zone zero series character

• wuthering waves series character

• hololive from justice and dev is

• HSR character from 2.2 - 2.5 version

• tokidoki bosotto roshia-go de dereru tonari no alya-san series

For character prompts, please refer to the Danbooru site for accurate tags and references.

License

Fair AI Public License 1.0-SD